2 papers
cs.LG2020
Physical System for Non Time Sequence Data
Xiongren Chen
We propose a novelty approach to connect machine learning to causal structure learning by jacobian matrix of neural network w.r.t. input variables. In this paper, we extend the jac…
cs.LG2020
Gradient-based Causal Structure Learning with Normalizing Flow
Xiongren Chen
In this paper, we propose a score-based normalizing flow method called DAG-NF to learn dependencies of input observation data. Inspired by Grad-CAM in computer vision, we use jacob…